Files
claude-skills/hermes/mapping.yaml
vitya 6b36b312fa feat(hermes): MVP converter + 4 universal skills converted
Adds the conversion infrastructure for the Hermes-rollout (Nous Research):

- hermes/mapping.yaml — per-skill schema (mode: auto|manual|skip|pending,
  category, replace-rules, source override). Every skills/<name>/ has an
  explicit entry; the build fails on unmapped skills.
- scripts/build-hermes.py — Python converter. Reads mapping.yaml; for auto
  applies replace-rules to SKILL.md and copies the rest verbatim; for manual
  copies hermes/skills/<source>/ as-is; for skip / pending records to
  dist-hermes/SKIPPED.md.
- dist-hermes/ — pre-converted Hermes-flavour tree (committed; consumed by
  the recursive installer in [hermes-installer-skill]). Includes 4 universal
  skills: pulling-before-work, active-platform (with Linux+bash replacement
  rule), project-discipline, using-markitdown. Plus SKIPPED.md listing
  8 skip + 10 pending entries.
- README.md — adds "Build for Hermes" section, updates layout, mentions
  hermes/, dist-hermes/, build-hermes.py.

Mapping is the source of truth for the audit table from
.wiki/concepts/hermes-skills-rollout-design.md (Q1-Q8). Pending entries
preserve the audit decision (intended mode/category) for the follow-up
tasks: hermes-flavour-mcp-setups, hermes-installer-skill,
hermes-mvp-coverage. Security carry-forward (extraheader-pattern,
POSIX-absolute paths, semver bumps) — infrastructure ready (replace-rules +
manual mode); concrete content lands in hermes-flavour-mcp-setups.

Smoke-tests: idempotent re-run produces no diff; replace-rules verified on
active-platform (Linux+bash); strict-mapping fail-fast verified on a
synthetic unmapped skill (exit 1).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 00:00:00 +03:00

162 lines
5.2 KiB
YAML

# Hermes Skills Rollout — mapping
#
# Source of truth for the converter (scripts/build-hermes.py).
# EVERY skill in skills/ MUST appear in `skills:` exactly once — the build
# fails on unmapped skills (forces an explicit decision per skill).
#
# Modes:
# auto — convert from skills/<name>/, applying replace-rules. Lands in
# dist-hermes/<category>/<name>/.
# manual — copy from `source:` directory verbatim (no replace-rules).
# Used for Hermes-flavour rewrites (e.g. yaml-edit MCP setups).
# skip — audited as not-applicable; recorded in dist-hermes/SKIPPED.md.
# pending — present in mapping but not yet built; recorded in SKIPPED.md.
# `intended:` block declares the future mode/category, so the
# audit table is preserved across MVP iterations.
#
# Categories: software-development | productivity | mcp | research | meta
#
# See .wiki/concepts/hermes-skills-rollout-design.md for the full audit
# (Q1-Q8 + the 21-row decision table).
version: 1
hermes:
installer_path: meta/claude-skills-installer
default_category: software-development
categories:
- software-development
- productivity
- mcp
- research
- meta
skills:
# ─── auto (4 universals — MVP target) ────────────────────────────────
pulling-before-work:
mode: auto
category: software-development
active-platform:
mode: auto
category: software-development
replace-rules:
- find: "**Windows + PowerShell.**"
replace: "**Linux + bash.**"
reason: "Hermes runs on Linux factory machines (/opt/data/projects). Default platform shifts."
- find: "Use this until something in the session tells you to switch. Reason: the user's primary workstation is Windows."
replace: "Use this until something in the session tells you to switch. Reason: Hermes runs on Linux factory machines."
reason: "Mirror reasoning sentence to match the new default."
project-discipline:
mode: auto
category: software-development
using-markitdown:
mode: auto
category: productivity
# ─── skip (8 — audited as not-applicable) ────────────────────────────
caveman:
mode: skip
reason: "Hermes runs on glm-5.1 (cheap local model); token-compression motive disappears."
caveman-commit:
mode: skip
reason: "Caveman family — cheap-model context, no compression motive."
caveman-compress:
mode: skip
reason: "Caveman family — cheap-model context, no compression motive."
caveman-help:
mode: skip
reason: "Help-card for the caveman family which itself is skipped."
caveman-review:
mode: skip
reason: "Caveman family — cheap-model context, no compression motive."
setup-interns:
mode: skip
reason: "Hermes itself is a cheap-intern model — the delegation tier collapses."
using-interns:
mode: skip
reason: "Hermes itself is a cheap-intern model — the delegation tier collapses."
find-skills:
mode: skip
reason: "Hermes has built-in skills_list() / progressive disclosure."
# ─── pending (10 — deferred to follow-up tasks) ──────────────────────
setup-tasks:
mode: pending
reason: "Pending hermes-mvp-coverage."
intended:
mode: auto
category: productivity
using-tasks:
mode: pending
reason: "Pending hermes-mvp-coverage."
intended:
mode: auto
category: productivity
setup-wiki:
mode: pending
reason: "Pending hermes-mvp-coverage. Hermes ships research/llm-wiki — our schema is preserved via override-precedence."
intended:
mode: auto
category: research
using-wiki:
mode: pending
reason: "Pending hermes-mvp-coverage. Hermes ships research/llm-wiki — our schema is preserved via override-precedence."
intended:
mode: auto
category: research
setup-projects-meta:
mode: pending
reason: "Pending hermes-flavour-mcp-setups: rewrite as yaml-edit ~/.hermes/config.yaml plus pre-check + extraheader fallback."
intended:
mode: manual
source: hermes/skills/setup-projects-meta
category: mcp
using-projects-meta:
mode: pending
reason: "Pending hermes-mvp-coverage."
intended:
mode: auto
category: mcp
setup-context7:
mode: pending
reason: "Pending hermes-flavour-mcp-setups: rewrite as yaml-edit ~/.hermes/config.yaml."
intended:
mode: manual
source: hermes/skills/setup-context7
category: mcp
using-context7:
mode: pending
reason: "Pending hermes-mvp-coverage."
intended:
mode: auto
category: mcp
project-bootstrap:
mode: pending
reason: "Pending hermes-mvp-coverage. Orchestrator — adapts last; CLAUDE.md trigger-lines drop (Hermes auto-discovers)."
intended:
mode: auto
category: software-development
recommend-dont-menu:
mode: pending
reason: "Added 2026-05-06 after the original audit. Cross-agent applicability claimed (response-style rule) — Hermes-side audit not yet done."
intended:
mode: auto
category: productivity